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. 11-RESID-POST-AA
    6. 58610
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    Cham
    -0.08
    .console
    -0.08
    ;}↵
    -0.07
     cinematic
    -0.07
     Ovo
    -0.07
    };↵↵//
    -0.07
    }↵↵↵
    -0.07
    }")↵
    -0.06
    -0.06
    ासन
    -0.06
    POSITIVE LOGITS
     बल्कि
    0.10
     încă
    0.10
     vielmehr
    0.09
    коп
    0.09
     بلکه
    0.08
    。しかし
    0.08
     Heide
    0.08
    кир
    0.08
    mittelt
    0.08
     بلکہ
    0.08
    Activations Density 0.063%

    No Known Activations