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. 372
    Prev
    Next
    INDEX
    Explanations

    Counting characters in strings

    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
     ويس
    -0.08
     Alexis
    -0.08
    ясь
    -0.08
     Komment
    -0.08
    ث
    -0.08
    elt
    -0.07
     الكتب
    -0.07
    Mens
    -0.07
     honra
    -0.07
    'organ
    -0.07
    POSITIVE LOGITS
    UTF
    0.07
    umul
    0.07
     дол
    0.07
     chron
    0.07
    .dump
    0.07
     sesame
    0.07
     Farming
    0.07
     sterling
    0.07
    gede
    0.07
    UMP
    0.07
    Activations Density 0.020%

    No Known Activations