© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 45351
    Prev
    Next
    INDEX
    Explanations

    names

    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
    ting
    -0.09
    uded
    -0.08
    nation
    -0.08
    usions
    -0.08
     Вы
    -0.08
     Hass
    -0.08
    �
    -0.07
    urer
    -0.07
    Pf
    -0.07
    148
    -0.07
    POSITIVE LOGITS
     William
    0.10
     Edison
    0.09
     Columb
    0.09
     Yale
    0.08
     carbonate
    0.08
     Edward
    0.08
     Shakespeare
    0.08
     Freeman
    0.08
     Roosevelt
    0.08
     Styled
    0.07
    Activations Density 0.134%

    No Known Activations