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

    Neuronpedia

    APICircuit 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. 30589
    Prev
    Next
    INDEX
    Explanations

    Softened ingredients/temperature

    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
     Rece
    -0.09
    _rece
    -0.09
     Verarbeitung
    -0.08
     받
    -0.08
     معالجة
    -0.08
     recepción
    -0.08
    (receiver
    -0.08
    _RECE
    -0.08
    Rece
    -0.08
     flagged
    -0.08
    POSITIVE LOGITS
     fluff
    0.09
    amut
    0.08
     دام
    0.08
    .arm
    0.08
    ని
    0.08
     whirlwind
    0.07
    -aged
    0.07
     шарт
    0.07
     noises
    0.07
    yx
    0.07
    Activations Density 0.001%

    No Known Activations