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. 41980
    Prev
    Next
    INDEX
    Explanations

    ary

    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
    _rb
    -0.08
    ofan
    -0.08
    TXT
    -0.07
    妻
    -0.07
    作者
    -0.07
    Tam
    -0.07
    WU
    -0.07
    (IF
    -0.07
     Authorization
    -0.07
    (isset
    -0.07
    POSITIVE LOGITS
     والث
    0.08
     derfor
    0.08
     ولذلك
    0.07
     Preto
    0.07
     Branco
    0.07
    óveis
    0.07
    ൽക
    0.07
     therefore
    0.07
     profundidad
    0.07
     threaded
    0.07
    Activations Density 0.001%

    No Known Activations