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. 12778
    Prev
    Next
    INDEX
    Explanations

    Quantities or amounts

    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
    Chap
    -0.08
    exact
    -0.08
    ocalypse
    -0.08
    umacher
    -0.07
    _js
    -0.07
    ح
    -0.07
     Particular
    -0.07
    ב
    -0.07
    ológicas
    -0.07
    Xu
    -0.07
    POSITIVE LOGITS
     almeno
    0.13
     mindestens
    0.13
     minstens
    0.10
     לפחות
    0.10
     atleast
    0.09
     minimaal
    0.09
     mindst
    0.09
     preferably
    0.09
    ,否则
    0.09
    至少
    0.09
    Activations Density 0.045%

    No Known Activations