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. 49226
    Prev
    Next
    INDEX
    Explanations

    `_stdio`

    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
    bell
    -0.07
    ظم
    -0.07
    Bell
    -0.07
    or
    -0.07
    فع
    -0.07
    _FULL
    -0.07
    ổ
    -0.07
    full
    -0.07
     Seah
    -0.07
     ::=
    -0.07
    POSITIVE LOGITS
     Desc
    0.09
     Efficiency
    0.08
     efficiency
    0.08
    -paced
    0.08
    onka
    0.08
     connection
    0.08
    548
    0.07
     Swap
    0.07
    (JS
    0.07
     transparency
    0.07
    Activations Density 0.001%

    No Known Activations