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. 58144
    Prev
    Next
    INDEX
    Explanations

    fall

    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
    _INS
    -0.08
     inconvenience
    -0.08
    rir
    -0.08
     fine
    -0.07
    тора
    -0.07
     knobs
    -0.07
     ಕೋಟ
    -0.07
     concentra
    -0.07
     menikmati
    -0.07
    _ins
    -0.07
    POSITIVE LOGITS
     lethal
    0.08
     hjemme
    0.08
     FRAME
    0.08
    alliative
    0.08
     riesgos
    0.08
    森林
    0.07
    危险
    0.07
     deadly
    0.07
     Bark
    0.07
    ez
    0.07
    Activations Density 0.005%

    No Known Activations