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. 58725
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Andrew
    -0.09
    Andrew
    -0.08
     metus
    -0.08
     Camden
    -0.08
     hing
    -0.07
     mahs
    -0.07
     tul
    -0.07
    scr
    -0.07
    bie
    -0.07
    erd
    -0.07
    POSITIVE LOGITS
    λει
    0.08
     disciplina
    0.07
     Dingen
    0.07
     different
    0.07
     operadores
    0.07
     separate
    0.07
    .Space
    0.07
     日
    0.07
    _funcs
    0.07
     bubble
    0.07
    Activations Density 0.000%

    No Known Activations