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. 15-RESID-POST-AA
    6. 19081
    Prev
    Next
    INDEX
    Explanations

    woman's

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _REGEX
    -0.08
    ثمر
    -0.08
    Remarks
    -0.08
    (to
    -0.08
    100
    -0.07
    Thirty
    -0.07
     emphas
    -0.07
    (Json
    -0.07
    Since
    -0.07
     вывести
    -0.07
    POSITIVE LOGITS
     hohe
    0.09
     उच्च
    0.09
     vysok
    0.09
     hohen
    0.08
     droit
    0.08
     hoher
    0.08
     hoge
    0.08
     ઉચ્ચ
    0.08
    icie
    0.08
     yüksek
    0.08
    Activations Density 0.000%

    No Known Activations