© 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. 51178
    Prev
    Next
    INDEX
    Explanations

    is

    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
     practicality
    -0.10
    合法
    -0.09
     anonymity
    -0.09
     legality
    -0.09
     authorized
    -0.09
    ações
    -0.09
     Proper
    -0.09
     stabilité
    -0.09
     complexities
    -0.08
     ness
    -0.08
    POSITIVE LOGITS
     incorrect
    0.21
     inaccurate
    0.18
     false
    0.17
     wrong
    0.17
    incorrect
    0.16
    Incorrect
    0.16
     flawed
    0.15
    false
    0.14
     INC
    0.14
     Incorrect
    0.14
    Activations Density 0.046%

    No Known Activations