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. 53270
    Prev
    Next
    INDEX
    Explanations

    inaugural or first class

    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
     Saint
    -0.08
     welk
    -0.08
     Ansicht
    -0.08
    ých
    -0.08
    redirect
    -0.07
     Ine
    -0.07
    ఖ
    -0.07
    ින්
    -0.07
    _SHIFT
    -0.07
     coraz
    -0.07
    POSITIVE LOGITS
     inaugural
    0.15
     pioneers
    0.12
     pioneer
    0.11
     founder
    0.11
     founding
    0.11
     Founder
    0.11
     pioneering
    0.10
    Founder
    0.10
     pione
    0.10
     founders
    0.10
    Activations Density 0.105%

    No Known Activations