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. 130286
    Prev
    Next
    INDEX
    Explanations

    Principled BSDF

    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
    _recursive
    -0.09
    count
    -0.08
     Bg
    -0.08
    recursive
    -0.08
     FRIEND
    -0.08
     counted
    -0.08
    	count
    -0.08
     recursively
    -0.07
    _counts
    -0.07
    counts
    -0.07
    POSITIVE LOGITS
     payoff
    0.10
    (material
    0.08
     palette
    0.08
     Stacey
    0.08
     terrain
    0.08
     payout
    0.08
     drivetrain
    0.08
     materiales
    0.07
     pembayaran
    0.07
    روی
    0.07
    Activations Density 0.001%

    No Known Activations