© 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. 1431
    Prev
    Next
    INDEX
    Explanations

    soaring

    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
     sting
    -0.08
    બર
    -0.07
    mel
    -0.07
     nd
    -0.07
     Swe
    -0.07
     MLA
    -0.07
     konst
    -0.07
    wez
    -0.07
     houver
    -0.07
     tingkat
    -0.07
    POSITIVE LOGITS
    ût
    0.08
     Kent
    0.08
     trot
    0.08
    Fan
    0.08
     skinny
    0.08
    Hung
    0.07
    'im
    0.07
    潮
    0.07
     Cutter
    0.07
     handsome
    0.07
    Activations Density 0.007%

    No Known Activations