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. 112036
    Prev
    Next
    INDEX
    Explanations

    +

    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
     Hydra
    -0.08
    ző
    -0.08
    Wax
    -0.07
    (;
    -0.07
    hes
    -0.07
     Mediterr
    -0.07
     weighting
    -0.07
     isteyen
    -0.07
    avar
    -0.07
    细
    -0.07
    POSITIVE LOGITS
     إع
    0.08
     monop
    0.08
     convey
    0.07
     التنمية
    0.07
     scint
    0.07
     bera
    0.07
     Bass
    0.07
     rad
    0.07
     soud
    0.07
    give
    0.07
    Activations Density 0.001%

    No Known Activations