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. 23440
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     clam
    -0.07
    �
    -0.07
    imator
    -0.07
    gments
    -0.07
     Gl
    -0.07
     Donovan
    -0.07
    cedure
    -0.07
     이
    -0.07
    üh
    -0.06
    POSITIVE LOGITS
     zumindest
    0.11
     wünschen
    0.09
     toplant
    0.09
    contest
    0.08
     yp
    0.08
     opl
    0.08
     där
    0.08
     yrs
    0.08
    πι
    0.08
    инград
    0.08
    Activations Density 0.055%

    No Known Activations