© 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. 5899
    Prev
    Next
    INDEX
    Explanations

    SOL

    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
     mf
    -0.09
    skat
    -0.09
    [size
    -0.08
    mill
    -0.08
    ník
    -0.08
     milion
    -0.08
    ింప
    -0.08
     MB
    -0.08
     wille
    -0.08
    ée
    -0.07
    POSITIVE LOGITS
    ID
    0.11
    idity
    0.10
     அன
    0.09
    િડ
    0.09
    ids
    0.09
    UTIONS
    0.08
    idar
    0.08
    idiendo
    0.08
    idir
    0.08
    IDS
    0.08
    Activations Density 0.003%

    No Known Activations