© 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. 47156
    Prev
    Next
    INDEX
    Explanations

    snap

    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
    治疗
    -0.08
    ραπε
    -0.08
    iril
    -0.07
    �
    -0.07
    iyana
    -0.07
    Cela
    -0.07
    iray
    -0.07
    amo
    -0.07
     لح
    -0.07
     dargestellt
    -0.07
    POSITIVE LOGITS
     Flex
    0.09
     夜
    0.08
    .deep
    0.07
     prover
    0.07
     Chiefs
    0.07
    Flex
    0.07
    ('*
    0.07
     cua
    0.07
     flexibil
    0.07
     Springs
    0.07
    Activations Density 0.001%

    No Known Activations