© 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. 112509
    Prev
    Next
    INDEX
    Explanations

    punctuation and grammar

    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
     falta
    -0.08
     discrimination
    -0.08
    競
    -0.08
     touchdown
    -0.07
     training
    -0.07
    );}
    -0.07
     disciplines
    -0.07
     hunt
    -0.07
     rival
    -0.07
     integer
    -0.07
    POSITIVE LOGITS
     الأوسط
    0.09
    Quoted
    0.09
    Separated
    0.09
    _Handle
    0.08
    _Admin
    0.08
    Middle
    0.08
    Collateral
    0.08
    Handled
    0.08
    Oliver
    0.08
    _String
    0.08
    Activations Density 0.004%

    No Known Activations