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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 76088
    Prev
    Next
    INDEX
    Explanations

    compiling code

    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
     Instagram
    -0.08
     बातचीत
    -0.08
     Conversation
    -0.08
    _person
    -0.07
     కేంద్ర
    -0.07
     keskust
    -0.07
     vielf
    -0.07
     Probability
    -0.07
     punct
    -0.07
    (t
    -0.07
    POSITIVE LOGITS
     compilation
    0.12
    Compile
    0.11
    _compile
    0.11
     compiling
    0.11
    Compilation
    0.11
     producing
    0.10
     gcc
    0.10
     assembler
    0.10
     Compilation
    0.10
     trava
    0.10
    Activations Density 0.022%

    No Known Activations