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. 53819
    Prev
    Next
    INDEX
    Explanations

    suicide prevention hotlines

    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
    óla
    -0.10
    აზი
    -0.09
    Portable
    -0.09
     שהוא
    -0.08
     flora
    -0.08
     vieles
    -0.08
     отды
    -0.08
    ��
    -0.08
    ന്ത
    -0.08
    omena
    -0.08
    POSITIVE LOGITS
     transferring
    0.08
     stanza
    0.08
    wiki
    0.08
     transfers
    0.08
     transfer
    0.08
    i
    0.08
     Herzog
    0.07
     constant
    0.07
    章节
    0.07
     trasfer
    0.07
    Activations Density 0.000%

    No Known Activations