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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 60535
    Prev
    Next
    INDEX
    Explanations

    rd

    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
    igste
    -0.08
    ళ్ల
    -0.08
     ada
    -0.07
     telah
    -0.07
    -0.07
     ISS
    -0.07
     уступ
    -0.07
    isu
    -0.07
     предлагает
    -0.07
     INVENT
    -0.07
    POSITIVE LOGITS
    .Lib
    0.08
    _bound
    0.07
    .bound
    0.07
    _lib
    0.07
    Bound
    0.07
     힘
    0.07
    PP
    0.07
     ár
    0.07
    -bound
    0.07
    Mgr
    0.07
    Activations Density 0.000%

    No Known Activations