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. 9211
    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
    114
    -0.07
    140
    -0.07
    koj
    -0.07
     stand
    -0.07
    jede
    -0.07
     phy
    -0.07
    124
    -0.07
    uyen
    -0.07
    广大
    -0.07
    >You
    -0.06
    POSITIVE LOGITS
    開始
    0.09
    temporary
    0.09
     anew
    0.09
     начале
    0.09
    増
    0.09
    Inicio
    0.09
     inception
    0.09
     Inicio
    0.08
    入住
    0.08
    тием
    0.08
    Activations Density 0.026%

    No Known Activations