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. 102927
    Prev
    Next
    INDEX
    Explanations

    than

    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
    до
    -0.08
     Excellent
    -0.07
    jong
    -0.07
     excellent
    -0.07
    -style
    -0.07
     далеко
    -0.07
    -appointed
    -0.07
    "}},↵
    -0.07
    /";↵↵
    -0.07
     весьма
    -0.07
    POSITIVE LOGITS
     delitos
    0.08
     sonora
    0.08
     sonidos
    0.08
    ovati
    0.08
     parë
    0.08
     kuti
    0.08
     penal
    0.08
     nigbati
    0.07
     nigba
    0.07
     esti
    0.07
    Activations Density 0.014%

    No Known Activations