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. 119259
    Prev
    Next
    INDEX
    Explanations

    volatile

    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
     Sherman
    -0.08
     fico
    -0.08
    ktf
    -0.08
     androgen
    -0.08
    Collateral
    -0.08
     Cyber
    -0.08
     IDX
    -0.08
     Ft
    -0.08
     electroph
    -0.08
     marvel
    -0.08
    POSITIVE LOGITS
     expelled
    0.09
     minerals
    0.09
     bubbles
    0.08
     transported
    0.08
     extracted
    0.08
     provenant
    0.08
    �
    0.08
    .flatten
    0.08
    mant
    0.07
    需求
    0.07
    Activations Density 0.003%

    No Known Activations