Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12411
    Prev
    Next
    INDEX
    Explanations

    mathematical problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     agreeing
    -0.07
     Mp
    -0.07
     ان
    -0.07
     coated
    -0.07
    -fil
    -0.07
     infected
    -0.07
    339
    -0.07
     �
    -0.07
     agreed
    -0.07
     Fil
    -0.07
    POSITIVE LOGITS
    ↵///
    0.08
     Macy
    0.08
     서
    0.08
    yet
    0.07
     cello
    0.07
     erotische
    0.07
     doga
    0.07
    والی
    0.07
    @Required
    0.07
     Getter
    0.07
    Activations Density 1.422%

    No Known Activations