© 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. 6122
    Prev
    Next
    INDEX
    Explanations

    arrow symbol

    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
     contextual
    -0.08
     commands
    -0.08
     context
    -0.08
    ilever
    -0.08
    ã
    -0.07
     overflow
    -0.07
     RESET
    -0.07
    iel
    -0.07
     resets
    -0.07
     CLEAN
    -0.07
    POSITIVE LOGITS
    _windows
    0.09
     trees
    0.08
    windows
    0.08
    Windows
    0.08
    _regions
    0.08
    Policies
    0.08
     arbres
    0.08
     fenêtres
    0.08
     árvores
    0.08
     casamento
    0.08
    Activations Density 0.002%

    No Known Activations