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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1460
    Prev
    Next
    INDEX
    Explanations

    geometry labels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     penc
    -0.08
    ुत
    -0.07
    čko
    -0.07
    -cond
    -0.07
     Stol
    -0.07
    ုံး
    -0.07
     quarantine
    -0.07
    erns
    -0.07
    ót
    -0.07
     Yay
    -0.07
    POSITIVE LOGITS
     নেত
    0.08
     للو
    0.08
     мужчины
    0.08
    _datetime
    0.08
     Killer
    0.07
    crime
    0.07
    Male
    0.07
     предполага
    0.07
     Mur
    0.07
     клиента
    0.07
    Activations Density 0.068%

    No Known Activations