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. 58673
    Prev
    Next
    INDEX
    Explanations

    two

    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
     Dough
    -0.09
     Tas
    -0.08
    Tas
    -0.08
    เส
    -0.08
    ez
    -0.07
     Luiz
    -0.07
     routinely
    -0.07
     footprint
    -0.07
    origine
    -0.07
     Medieval
    -0.07
    POSITIVE LOGITS
     jewe
    0.08
     cran
    0.08
     asc
    0.08
    ulu
    0.08
     đỏ
    0.07
     стат
    0.07
     bell
    0.07
    ۇن
    0.07
     forty
    0.07
     bee
    0.07
    Activations Density 0.029%

    No Known Activations