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. 65128
    Prev
    Next
    INDEX
    Explanations

    }

    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
    Workbook
    -0.09
     chandelier
    -0.09
     pne
    -0.08
     workbook
    -0.08
     chand
    -0.08
     satış
    -0.08
     দ্র
    -0.08
     brokerage
    -0.08
    חן
    -0.08
     broth
    -0.08
    POSITIVE LOGITS
     indices
    0.08
     tolerate
    0.08
     Manuel
    0.07
    vertheless
    0.07
     ٽ
    0.07
     accepte
    0.07
    JSON
    0.07
     segue
    0.07
    .zero
    0.07
     akzept
    0.07
    Activations Density 0.132%

    No Known Activations