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. 120466
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     tenant
    -0.08
     பூ
    -0.07
     ہوتے
    -0.07
     اینترنت
    -0.07
     invece
    -0.07
     کرتے
    -0.07
     tenants
    -0.07
     Laf
    -0.07
     tirer
    -0.07
    iern
    -0.07
    POSITIVE LOGITS
    uuml
    0.08
     zahr
    0.08
    поч
    0.07
     diet
    0.07
    cadena
    0.07
    dess
    0.07
    ешь
    0.07
    "}↵
    0.07
    "`↵↵
    0.07
    "]↵
    0.07
    Activations Density 0.000%

    No Known Activations