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. 11738
    Prev
    Next
    INDEX
    Explanations

    SQL queries

    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
     Eg
    -0.08
     Mee
    -0.08
    itaa
    -0.07
    য়
    -0.07
    WAYS
    -0.07
     attained
    -0.07
    ņa
    -0.07
    _SB
    -0.07
     pè
    -0.07
    -0.07
    POSITIVE LOGITS
     WHERE
    0.08
     abon
    0.07
     grab
    0.07
    >,
    0.07
    zf
    0.07
    grab
    0.07
    �
    0.07
    �
    0.07
    lend
    0.07
     happens
    0.07
    Activations Density 0.003%

    No Known Activations