© 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. 24642
    Prev
    Next
    INDEX
    Explanations

    empty nest

    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
     טוב
    -0.08
    _feedback
    -0.08
    וואַ
    -0.08
    את
    -0.08
     wastewater
    -0.08
     קיין
    -0.08
    emies
    -0.08
    feedback
    -0.07
     רב
    -0.07
    免
    -0.07
    POSITIVE LOGITS
     conviction
    0.08
    ......
    0.08
     nationalist
    0.08
    %^
    0.08
    .TAG
    0.07
     Gior
    0.07
     Normalize
    0.07
    .B
    0.07
     Bab
    0.07
     resonance
    0.07
    Activations Density 0.005%

    No Known Activations