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. 53455
    Prev
    Next
    INDEX
    Explanations

    极

    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
     cf
    -0.08
    tong
    -0.08
     Gail
    -0.08
     Ezek
    -0.08
     Francis
    -0.07
     pamph
    -0.07
     Raymond
    -0.07
     illet
    -0.07
     Orig
    -0.07
     Cai
    -0.07
    POSITIVE LOGITS
    玩的
    0.07
    istic
    0.07
    istically
    0.07
     snowy
    0.07
    VER
    0.07
    _WS
    0.07
    -den
    0.07
    써
    0.07
     Abr
    0.07
     skew
    0.07
    Activations Density 0.003%

    No Known Activations