Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 105990
    Prev
    Next
    INDEX
    Explanations

    crime

    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
     городской
    -0.07
     Stadt
    -0.07
     Inclusion
    -0.07
     city
    -0.07
    🏼
    -0.07
     chaînes
    -0.07
     spe
    -0.07
    ையில்
    -0.07
     peça
    -0.07
     elite
    -0.07
    POSITIVE LOGITS
     tempus
    0.09
     fiduci
    0.09
     выбора
    0.08
    _SUPPORTED
    0.08
     کب
    0.08
     MYSQL
    0.08
    固
    0.08
     المن
    0.08
     deeds
    0.08
    Vic
    0.08
    Activations Density 0.007%

    No Known Activations