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. 11-RESID-POST-AA
    6. 90258
    Prev
    Next
    INDEX
    Explanations

    coding formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Overrides
    -0.09
    Override
    -0.08
    .Path
    -0.08
    Utility
    -0.08
     Basel
    -0.08
    .enum
    -0.07
     подпис
    -0.07
     overrides
    -0.07
    .Base
    -0.07
    _override
    -0.07
    POSITIVE LOGITS
     whitespace
    0.10
     spacing
    0.10
     spaces
    0.10
    Whitespace
    0.09
    (space
    0.09
     Komm
    0.09
     separating
    0.08
     것
    0.08
    फल
    0.08
     espaços
    0.08
    Activations Density 0.041%

    No Known Activations