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. 87975
    Prev
    Next
    INDEX
    Explanations

    crank

    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
    ↵   ↵
    -0.08
     vex
    -0.07
     flog
    -0.07
    .codes
    -0.07
     fx
    -0.07
     quilting
    -0.07
     fluent
    -0.07
     nggawe
    -0.07
     deepcopy
    -0.07
     continuum
    -0.07
    POSITIVE LOGITS
     Homer
    0.09
    prote
    0.08
     childhood
    0.08
    iett
    0.08
    font
    0.08
    -on
    0.07
     Tol
    0.07
    ොර
    0.07
    -your
    0.07
     =$
    0.07
    Activations Density 0.001%

    No Known Activations