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. 130896
    Prev
    Next
    INDEX
    Explanations

    Sampling methods

    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
    icultural
    -0.09
    éric
    -0.08
    icana
    -0.08
    aanik
    -0.08
    ernos
    -0.08
    ergenic
    -0.08
    owering
    -0.08
    াং
    -0.08
    avanaugh
    -0.08
     pret
    -0.08
    POSITIVE LOGITS
    .sample
    0.09
     sample
    0.08
     Sample
    0.08
    _sample
    0.08
    Sample
    0.08
     Gilles
    0.08
     மாத
    0.08
     intervalo
    0.08
     Ohne
    0.08
     Gior
    0.08
    Activations Density 0.007%

    No Known Activations