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. 98419
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    Including
    -0.11
    Vielleicht
    -0.11
    Estamos
    -0.10
    Même
    -0.10
    Whether
    -0.10
    Crear
    -0.10
    Puede
    -0.10
    Seleccion
    -0.10
     weren't
    -0.10
     They'll
    -0.10
    POSITIVE LOGITS
     =>
    0.18
     gives
    0.18
     →
    0.15
     
    0.15
     ->
    0.15
      
    0.14
     implies
    0.13
    =>
    0.13
     giving
    0.13
     ==>
    0.13
    Activations Density 0.213%

    No Known Activations