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. 12941
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     inm
    -0.08
    eins
    -0.07
    -0.07
    _movies
    -0.07
    otyp
    -0.07
    etric
    -0.07
     αντιμε
    -0.07
     nightly
    -0.07
    Trips
    -0.07
    -0.07
    POSITIVE LOGITS
    লাম
    0.09
     elabor
    0.08
    லாம்
    0.08
    يمين
    0.07
     आदि
    0.07
     že
    0.07
     references
    0.07
     toh
    0.07
     antwort
    0.07
    References
    0.07
    Activations Density 0.023%

    No Known Activations