© 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. 7-RESID-POST-AA
    11. 1318
    Prev
    Next
    INDEX
    Explanations

    thermal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sky
    -0.08
    .sky
    -0.08
    Sky
    -0.08
     તે
    -0.07
     moss
    -0.07
     sky
    -0.07
    _SK
    -0.07
     homo
    -0.07
     ની
    -0.07
     નો
    -0.07
    POSITIVE LOGITS
     cow
    0.09
    0.08
     BC
    0.07
     Buffalo
    0.07
     Apple
    0.07
     eingef
    0.07
     تۇ
    0.07
     brav
    0.07
     여
    0.07
    .ops
    0.07
    Activations Density 0.005%
    No Known Activations