© 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. 96898
    Prev
    Next
    INDEX
    Explanations

    arche

    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
    agh
    -0.09
    encer
    -0.08
    im
    -0.08
    ro
    -0.08
     deu
    -0.08
    ец
    -0.08
    ubu
    -0.08
    ummer
    -0.08
     rot
    -0.07
    	per
    -0.07
    POSITIVE LOGITS
    types
    0.18
    typ
    0.15
    typing
    0.14
    typed
    0.12
    otyping
    0.12
    typen
    0.12
    typically
    0.12
    models
    0.12
    otypes
    0.12
    lists
    0.11
    Activations Density 0.001%

    No Known Activations