© 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. 97392
    Prev
    Next
    INDEX
    Explanations

    il

    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
     సో
    -0.08
     demanda
    -0.08
     loj
    -0.08
     demand
    -0.07
    angang
    -0.07
    โล
    -0.07
    rola
    -0.07
     luck
    -0.07
     सो
    -0.07
     дж
    -0.07
    POSITIVE LOGITS
    recursive
    0.09
    Recursive
    0.09
    тардың
    0.08
     recursive
    0.08
     recital
    0.08
     edən
    0.08
    ların
    0.08
    -panel
    0.08
    _recursive
    0.07
    Panel
    0.07
    Activations Density 0.001%

    No Known Activations