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. 43994
    Prev
    Next
    INDEX
    Explanations

    audiobooks

    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
     signaling
    -0.08
     Signal
    -0.08
     Equation
    -0.08
     firing
    -0.08
    _signal
    -0.08
     contribut
    -0.08
     poka
    -0.07
     provocative
    -0.07
     pequ
    -0.07
     ontwerpen
    -0.07
    POSITIVE LOGITS
     audiobook
    0.14
     narrated
    0.11
     narration
    0.11
     Audible
    0.10
    朗
    0.10
     Voices
    0.09
    版
    0.09
     audi
    0.09
     voices
    0.09
     chewing
    0.09
    Activations Density 0.006%

    No Known Activations