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. 58850
    Prev
    Next
    INDEX
    Explanations

    corresponds

    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
    ivic
    -0.09
     boyunca
    -0.08
     informazioni
    -0.07
     burden
    -0.07
     Sens
    -0.07
     warn
    -0.07
     భార
    -0.07
    zicht
    -0.07
     wachsen
    -0.07
    ington
    -0.07
    POSITIVE LOGITS
    符合
    0.10
     matches
    0.09
    题
    0.09
    Matches
    0.09
    正确
    0.08
    _answer
    0.08
    arters
    0.08
     الصحيح
    0.08
    大小单双
    0.08
     сәйкес
    0.08
    Activations Density 0.020%

    No Known Activations