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. 120273
    Prev
    Next
    INDEX
    Explanations

    空

    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
     =====
    -0.09
     ainakin
    -0.08
     لكن
    -0.08
    ustri
    -0.08
    شت
    -0.08
    =NULL
    -0.07
    ellten
    -0.07
    ですが
    -0.07
     suitable
    -0.07
    .Bot
    -0.07
    POSITIVE LOGITS
     naked
    0.10
     numerical
    0.09
     frivol
    0.09
     gratuit
    0.09
     superficial
    0.08
    mere
    0.08
     Numerical
    0.08
     मेहन
    0.08
     rote
    0.08
     breeze
    0.07
    Activations Density 0.007%

    No Known Activations