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. 12059
    Prev
    Next
    INDEX
    Explanations

    phonetics

    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
     paranormal
    -0.09
     gallons
    -0.08
     blinds
    -0.08
     ужас
    -0.08
     Adirond
    -0.08
     gallon
    -0.08
     Parlamento
    -0.08
     waan
    -0.08
    /comments
    -0.08
     blinded
    -0.08
    POSITIVE LOGITS
     permissible
    0.08
     allowable
    0.08
     restricciones
    0.08
    (seq
    0.08
                                             
    0.08
    ീവ്
    0.08
    nh
    0.08
    (cs
    0.07
    CH
    0.07
    čky
    0.07
    Activations Density 0.008%

    No Known Activations