© 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. 2710
    Prev
    Next
    INDEX
    Explanations

    that

    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
     symposium
    -0.08
    stip
    -0.08
     ശക്ത
    -0.08
    േശ
    -0.07
    STR
    -0.07
     �
    -0.07
    امية
    -0.07
     স্প
    -0.07
     स्प
    -0.07
     efectivo
    -0.07
    POSITIVE LOGITS
    Colored
    0.08
     Colored
    0.08
     Ill
    0.08
    igo
    0.07
     Uph
    0.07
    న్ని
    0.07
     segreg
    0.07
     Fo
    0.07
    .cursor
    0.07
     Cart
    0.07
    Activations Density 0.000%

    No Known Activations