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. 112976
    Prev
    Next
    INDEX
    Explanations

    powerful historical women

    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
    hic
    -0.08
     chores
    -0.08
     exped
    -0.08
     responsabilidades
    -0.08
     conqu
    -0.07
     knocks
    -0.07
     ioutil
    -0.07
     fries
    -0.07
     fft
    -0.07
     బాధ
    -0.07
    POSITIVE LOGITS
     സംഗീത
    0.10
     संगीत
    0.09
     음악
    0.08
    .Play
    0.08
    .play
    0.08
     موسی
    0.08
    映画
    0.08
     Exceptional
    0.08
     playback
    0.08
    .U
    0.08
    Activations Density 0.008%

    No Known Activations