© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 63400
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     бро
    -0.08
    _percent
    -0.08
     XP
    -0.07
    bps
    -0.07
     identifies
    -0.07
    ographs
    -0.07
    _inverse
    -0.07
     flock
    -0.07
    	RTHOOK
    -0.07
    -0.07
    POSITIVE LOGITS
     accessible
    0.11
    共享
    0.11
     scope
    0.11
     Scope
    0.11
     глоб
    0.11
     außerhalb
    0.11
    /global
    0.11
    Across
    0.11
     outside
    0.10
    accessible
    0.10
    Activations Density 0.010%
    No Known Activations