© 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. 70256
    Prev
    Next
    INDEX
    Explanations

    bot responses

    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
    ٹرول
    -0.09
    olic
    -0.08
     тор
    -0.08
    uvieron
    -0.08
    لو
    -0.08
     آلاف
    -0.08
    �
    -0.08
    حدث
    -0.08
     الرجال
    -0.08
    ulega
    -0.08
    POSITIVE LOGITS
     purported
    0.08
     allegedly
    0.08
     alleged
    0.08
     accused
    0.08
     inderdaad
    0.08
    Masc
    0.08
    &aacute
    0.08
    0.08
     действительно
    0.07
     방식
    0.07
    Activations Density 0.256%
    No Known Activations