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. 88219
    Prev
    Next
    INDEX
    Explanations

    Given

    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
     बित
    -0.09
     ಮು
    -0.08
     witnessed
    -0.08
     Plac
    -0.08
     ಹಾಕ
    -0.08
     waterfront
    -0.08
     competitie
    -0.07
     plac
    -0.07
     davant
    -0.07
    ონს
    -0.07
    POSITIVE LOGITS
     $,
    0.08
     premise
    0.07
    .def
    0.07
    sons
    0.07
     kişiler
    0.07
    .kn
    0.07
    arf
    0.07
    情况下
    0.07
     الآ
    0.07
    _direction
    0.07
    Activations Density 0.017%

    No Known Activations