© 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. 29764
    Prev
    Next
    INDEX
    Explanations

    Quality and certainty

    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
    Sl
    -0.08
     Igu
    -0.08
    .La
    -0.08
    keypress
    -0.08
    payload
    -0.08
    (Locale
    -0.08
     graffiti
    -0.08
     subtly
    -0.07
     stunt
    -0.07
     creatively
    -0.07
    POSITIVE LOGITS
     തെള
    0.10
     evidence
    0.10
    -ranked
    0.10
     weaker
    0.10
     kakov
    0.09
     Evidence
    0.09
     strongest
    0.09
     stronger
    0.09
     ഗുര
    0.09
     weakest
    0.09
    Activations Density 0.004%

    No Known Activations