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. 23-RESID-POST-AA
    6. 98501
    Prev
    Next
    INDEX
    Explanations

    K

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    भार
    -0.08
    ONTO
    -0.08
     Repair
    -0.08
     plurality
    -0.08
    Rainbow
    -0.07
     repairing
    -0.07
     repair
    -0.07
    ωνα
    -0.07
    _SQL
    -0.07
     Rainbow
    -0.07
    POSITIVE LOGITS
    iş
    0.10
    endi
    0.09
    ot
    0.08
    020
    0.08
    ari
    0.08
    ુ
    0.07
    ష్ట
    0.07
     encontr
    0.07
    .aws
    0.07
     avere
    0.07
    Activations Density 0.001%

    No Known Activations