© 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. 23-RESID-POST-AA
    11. 6328
    Prev
    Next
    INDEX
    Explanations

    still

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     პლ
    -0.08
    <V
    -0.08
    <T
    -0.08
    өс
    -0.08
    ases
    -0.08
     თავიდან
    -0.08
    ീഷ
    -0.08
    онда
    -0.08
    ased
    -0.07
    мақ
    -0.07
    POSITIVE LOGITS
    still
    0.13
     still
    0.12
    仍
    0.12
     ještě
    0.11
     இன்ன
    0.11
     aún
    0.11
     ainda
    0.11
     Still
    0.11
     todavía
    0.11
    Still
    0.11
    Activations Density 0.071%

    No Known Activations