© 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. 26537
    Prev
    Next
    INDEX
    Explanations

    angle

    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
     lace
    -0.09
     은
    -0.08
     싶은
    -0.08
     balay
    -0.08
     decentral
    -0.07
     mobiles
    -0.07
     ביד
    -0.07
     bouch
    -0.07
     génére
    -0.07
     TEL
    -0.07
    POSITIVE LOGITS
    Radians
    0.12
     radians
    0.12
     cosine
    0.10
     hence
    0.09
     Nylon
    0.09
     angle
    0.08
     Celsius
    0.08
    .angle
    0.08
     угол
    0.08
     acquaintances
    0.08
    Activations Density 0.021%

    No Known Activations