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. 45411
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs and formulas

    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
    :nil
    -0.08
    nehmen
    -0.08
    obank
    -0.08
    thon
    -0.08
    rike
    -0.08
    шин
    -0.08
    embers
    -0.08
    inca
    -0.07
    ndir
    -0.07
    нии
    -0.07
    POSITIVE LOGITS
     harr
    0.09
     defensa
    0.09
     defesa
    0.08
     fraud
    0.08
     mailed
    0.08
     aver
    0.08
     Lamar
    0.07
     Liefer
    0.07
     casual
    0.07
     enga
    0.07
    Activations Density 0.025%

    No Known Activations