© 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. 11-RESID-POST-AA
    11. 111203
    Prev
    Next
    INDEX
    Explanations

    tub

    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
     Nam
    -0.08
     身
    -0.08
    wu
    -0.08
     Journ
    -0.07
    身份
    -0.07
     Arche
    -0.07
    권
    -0.07
     evangelical
    -0.07
     Orts
    -0.07
     dépos
    -0.07
    POSITIVE LOGITS
    �
    0.09
     topl
    0.09
     surf
    0.08
     verand
    0.08
     pia
    0.07
    /h
    0.07
     emoz
    0.07
     stu
    0.07
    Paypal
    0.07
     snork
    0.07
    Activations Density 0.003%

    No Known Activations