© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50472
    Prev
    Next
    INDEX
    Explanations

    Scripting paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Initialization
    -0.08
     Utilities
    -0.08
     Initialization
    -0.08
     Ability
    -0.08
     Value
    -0.08
     Characteristics
    -0.08
    abcdefgh
    -0.08
     Byte
    -0.08
     Character
    -0.08
     Appearance
    -0.08
    POSITIVE LOGITS
    BASEPATH
    0.16
    TARGET
    0.13
     target
    0.13
     TARGET
    0.12
     based
    0.12
    based
    0.12
    SCRIPT
    0.12
     dirname
    0.12
     tgt
    0.11
    target
    0.11
    Activations Density 0.025%

    No Known Activations