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. 78415
    Prev
    Next
    INDEX
    Explanations

    -|

    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
     Sich
    -0.09
    _SMALL
    -0.08
     Oro
    -0.08
     taka
    -0.08
    ETO
    -0.08
     iş
    -0.08
    _MAJOR
    -0.08
    Nk
    -0.07
     Chong
    -0.07
     Dob
    -0.07
    POSITIVE LOGITS
    Depart
    0.07
    chappen
    0.07
     Infect
    0.07
     nás
    0.07
    তি
    0.07
    arily
    0.07
     exper
    0.07
    clinic
    0.07
    clin
    0.07
    upal
    0.07
    Activations Density 0.002%

    No Known Activations