© 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. 108680
    Prev
    Next
    INDEX
    Explanations

    angles/degrees

    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
     Rhodes
    -0.09
     domination
    -0.08
     Donovan
    -0.08
    ోత
    -0.07
     Nazis
    -0.07
     targeted
    -0.07
     POW
    -0.07
     OWN
    -0.07
    etti
    -0.07
     relying
    -0.07
    POSITIVE LOGITS
     bend
    0.09
    wish
    0.08
     हल
    0.08
     beve
    0.08
    schrijving
    0.08
     curl
    0.08
     Ам
    0.08
     gently
    0.08
     配
    0.08
     cabinet
    0.08
    Activations Density 0.006%

    No Known Activations