© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29712
    Prev
    Next
    INDEX
    Explanations

    purpose

    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
    we
    -0.10
    pk
    -0.08
    SH
    -0.08
    sx
    -0.07
    NG
    -0.07
    219
    -0.07
    170
    -0.07
    speed
    -0.07
     arbor
    -0.07
    ISTRATION
    -0.07
    POSITIVE LOGITS
    fulness
    0.10
    fully
    0.09
    旨
    0.09
     назначения
    0.08
    ful
    0.08
    -packed
    0.08
    �
    0.07
     čl
    0.07
    icios
    0.07
     tou
    0.07
    Activations Density 0.016%

    No Known Activations