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. 53174
    Prev
    Next
    INDEX
    Explanations

    and

    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
     joking
    -0.08
     historian
    -0.08
     물론
    -0.08
     prophet
    -0.07
     migrate
    -0.07
    .Share
    -0.07
     Historic
    -0.07
     اول
    -0.07
     전문가
    -0.07
     Abbott
    -0.07
    POSITIVE LOGITS
     videoclip
    0.08
    bod
    0.08
     stairs
    0.08
     Angaben
    0.08
     lighting
    0.08
     sensory
    0.08
     sensual
    0.07
    -ear
    0.07
     tonic
    0.07
     storyboard
    0.07
    Activations Density 0.002%

    No Known Activations