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. 60894
    Prev
    Next
    INDEX
    Explanations

    stories

    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
     fynd
    -0.09
    ್�
    -0.08
     кредита
    -0.08
     modalities
    -0.08
     формат
    -0.08
    spiring
    -0.08
    JSONString
    -0.08
    _Asp
    -0.08
    erein
    -0.08
     сталки
    -0.08
    POSITIVE LOGITS
     representatives
    0.08
     representante
    0.08
    uin
    0.08
    ും
    0.08
     representative
    0.08
     représentants
    0.08
     representantes
    0.08
    代表
    0.08
     प्रतिनिध
    0.08
    Submit
    0.08
    Activations Density 0.166%

    No Known Activations