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. 49149
    Prev
    Next
    INDEX
    Explanations

    calculations and conversions

    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
    .sc
    -0.08
     parametros
    -0.08
    .Sc
    -0.08
    <Sc
    -0.07
    prepend
    -0.07
     SC
    -0.07
    TODO
    -0.07
    Helpers
    -0.07
    -spec
    -0.07
    .layer
    -0.07
    POSITIVE LOGITS
     notoriously
    0.10
     unusually
    0.09
     falsely
    0.09
     다음
    0.09
     surprisingly
    0.08
     traditionally
    0.08
     yum
    0.08
    _IMG
    0.08
    嫌
    0.08
     dubious
    0.08
    Activations Density 0.025%

    No Known Activations