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. 74458
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    يديا
    -0.08
    폐
    -0.08
    yeurs
    -0.08
    ketøy
    -0.08
     excluding
    -0.08
    ياً
    -0.08
    querque
    -0.08
    ่
    -0.08
    lüss
    -0.08
    زياء
    -0.08
    POSITIVE LOGITS
     elongated
    0.09
     ಅಭ್ಯರ್ಥ
    0.08
     후보
    0.08
    _PH
    0.08
    Thunk
    0.08
     candidat
    0.07
    BAC
    0.07
    candidate
    0.07
    trend
    0.07
     fuller
    0.07
    Activations Density 0.001%

    No Known Activations