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. 42000
    Prev
    Next
    INDEX
    Explanations

    down

    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
    க்கிய
    -0.10
     определения
    -0.08
     Absatz
    -0.08
    வில்லை
    -0.08
     bombing
    -0.07
    ங்கே
    -0.07
     મોડ
    -0.07
    ಸ್ಟ್
    -0.07
     Moore
    -0.07
     Bre
    -0.07
    POSITIVE LOGITS
    Chk
    0.07
     Todd
    0.07
    zí
    0.07
     unaffected
    0.07
    ônico
    0.07
    .fre
    0.07
    چی
    0.07
    Coef
    0.07
    0.07
     tüm
    0.07
    Activations Density 0.002%

    No Known Activations