Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 90191
    Prev
    Next
    INDEX
    Explanations

    Decimal digits

    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
    Legenda
    -0.08
    623
    -0.08
     mei
    -0.07
     분위
    -0.07
     durata
    -0.07
     Quest
    -0.07
     леген
    -0.07
     मैदान
    -0.07
    837
    -0.07
    雄
    -0.07
    POSITIVE LOGITS
     chopping
    0.09
    خلص
    0.08
     obtains
    0.08
    Screenshot
    0.08
    払
    0.08
    زالة
    0.08
     screenshot
    0.08
     trims
    0.08
    simulate
    0.08
    ந்த
    0.08
    Activations Density 0.007%

    No Known Activations