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. 106101
    Prev
    Next
    INDEX
    Explanations

    rules regarding phone/food/camera use

    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
    _regular
    -0.08
     accountant
    -0.08
    -billion
    -0.08
     nm
    -0.07
    irr
    -0.07
    Regular
    -0.07
    87
    -0.07
    89
    -0.07
    676
    -0.07
    67
    -0.07
    POSITIVE LOGITS
    は禁止
    0.12
     prohibited
    0.10
     prohibition
    0.09
    Muted
    0.09
    禁止
    0.09
     запрещ
    0.09
     excessive
    0.09
     отоп
    0.09
     reagent
    0.09
     yoyote
    0.09
    Activations Density 0.043%

    No Known Activations