© 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. 3-RESID-POST-AA
    11. 12777
    Prev
    Next
    INDEX
    Explanations

    less

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.08
     obje
    -0.08
     iniciativas
    -0.08
    Tracker
    -0.07
    RG
    -0.07
    ective
    -0.07
    _FACTOR
    -0.07
     venues
    -0.07
    ிங்
    -0.07
    _tracker
    -0.07
    POSITIVE LOGITS
     Sor
    0.08
     atent
    0.08
     Jul
    0.08
     chemotherapy
    0.08
     mur
    0.07
    ालय
    0.07
     Pietro
    0.07
    Sor
    0.07
    teborg
    0.07
    َه
    0.07
    Activations Density 0.003%

    No Known Activations