© 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. 65323
    Prev
    Next
    INDEX
    Explanations

    code

    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
     idiot
    -0.09
     nutzt
    -0.08
     prü
    -0.08
     portant
    -0.08
     krem
    -0.08
     dumpster
    -0.08
     sweaty
    -0.07
    WISE
    -0.07
     exorbit
    -0.07
     manche
    -0.07
    POSITIVE LOGITS
    <|reserved_200016|>
    0.09
    sil
    0.08
    add
    0.08
    _doc
    0.08
    iaz
    0.08
    ls
    0.08
    <|endoftext|>
    0.08
     �
    0.08
    acs
    0.07
     נ
    0.07
    Activations Density 0.026%

    No Known Activations