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. 111820
    Prev
    Next
    INDEX
    Explanations

    period

    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
     calculate
    -0.08
    bek
    -0.08
     visite
    -0.07
     rito
    -0.07
     белгил
    -0.07
     sym
    -0.07
     белг
    -0.07
    ക്കുന്ന
    -0.07
     raun
    -0.07
    calculate
    -0.07
    POSITIVE LOGITS
    Alternatively
    0.09
    Option
    0.09
    Plus
    0.08
     Plus
    0.08
     🙂
    0.08
     😉
    0.08
    option
    0.08
     :)
    0.08
    Good
    0.08
    aterdag
    0.08
    Activations Density 0.031%

    No Known Activations