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. 98119
    Prev
    Next
    INDEX
    Explanations

    say "%"

    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
    ────────────────
    -0.09
    Approx
    -0.09
    ="<
    -0.08
     approximate
    -0.08
    ='<
    -0.08
     aqui
    -0.08
    upakan
    -0.08
    ((*
    -0.08
     ((__
    -0.08
    approx
    -0.08
    POSITIVE LOGITS
     %
    0.26
    %
    0.23
    %
    0.17
    ٪
    0.16
    %,
    0.16
    %s
    0.15
     %↵
    0.15
     %%
    0.15
     `%
    0.15
     %}↵
    0.15
    Activations Density 0.030%

    No Known Activations