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. 98346
    Prev
    Next
    INDEX
    Explanations

    Other language

    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
    íst
    -0.10
    ades
    -0.09
    ów
    -0.08
    oli
    -0.08
    okuba
    -0.08
    og
    -0.08
    uthuk
    -0.08
    iri
    -0.08
    ovana
    -0.08
    oga
    -0.07
    POSITIVE LOGITS
    очь
    0.08
    et
    0.08
     focal
    0.08
    uc
    0.07
     existential
    0.07
    Suc
    0.07
    onies
    0.07
     weiß
    0.07
    Sizer
    0.07
    inaries
    0.07
    Activations Density 0.001%

    No Known Activations