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. 8716
    Prev
    Next
    INDEX
    Explanations

    formulas/code

    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
     থেকেই
    -0.10
     moisturizing
    -0.09
     বিচার
    -0.09
     marts
    -0.09
     seluruh
    -0.09
    രിച്ചു
    -0.08
     अगर
    -0.08
     മുഴ
    -0.08
     Danach
    -0.08
     weken
    -0.08
    POSITIVE LOGITS
     back
    0.07
    nu
    0.07
    .fac
    0.07
     seated
    0.07
    .back
    0.07
     prec
    0.07
     allocation
    0.07
     nu
    0.06
    109
    0.06
    .swap
    0.06
    Activations Density 0.000%

    No Known Activations