© 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. 96770
    Prev
    Next
    INDEX
    Explanations

    da

    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
    -0.07
     troubled
    -0.07
    Row
    -0.07
     pig
    -0.07
     bursting
    -0.07
     Row
    -0.07
    тав
    -0.07
    vig
    -0.07
    -0.07
    сив
    -0.07
    POSITIVE LOGITS
     واس
    0.08
     independence
    0.08
     considère
    0.08
    ának
    0.08
     indépendante
    0.08
     النوع
    0.08
    abetes
    0.07
     مقا
    0.07
     imprescindible
    0.07
     favorita
    0.07
    Activations Density 0.000%
    No Known Activations