© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47356
    Prev
    Next
    INDEX
    Explanations

    single quote

    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
     romano
    -0.08
     sports
    -0.08
     Ano
    -0.08
     humor
    -0.07
     FIFA
    -0.07
     revenue
    -0.07
     Amor
    -0.07
     located
    -0.07
     Subscription
    -0.07
     tim
    -0.07
    POSITIVE LOGITS
     buns
    0.09
    Adi
    0.08
     seachad
    0.08
     chow
    0.08
     egne
    0.08
    Till
    0.08
    /{{
    0.08
     preservation
    0.08
    १०
    0.08
    ибир
    0.08
    Activations Density 0.001%

    No Known Activations