Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 106315
    Prev
    Next
    INDEX
    Explanations

    Phenomenology

    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
    ב
    -0.09
    าหลี
    -0.08
    тік
    -0.08
    اون
    -0.08
    厕
    -0.08
    לה
    -0.08
    ราช
    -0.08
     //~
    -0.08
     Wiring
    -0.08
    קל
    -0.07
    POSITIVE LOGITS
     filóso
    0.08
     Zug
    0.07
    xr
    0.07
     sosp
    0.07
    ktf
    0.07
     philosoph
    0.07
    quential
    0.07
     launching
    0.07
     regarding
    0.07
     bezüglich
    0.07
    Activations Density 0.003%

    No Known Activations