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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111461
    Prev
    Next
    INDEX
    Explanations

    angles

    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
     Poi
    -0.07
     Hansen
    -0.07
     extraction
    -0.07
    pois
    -0.07
    azz
    -0.07
     Wis
    -0.07
    ോബ
    -0.07
    മ്മ
    -0.07
     Kaiser
    -0.07
    alan
    -0.07
    POSITIVE LOGITS
     clockwise
    0.11
     negativa
    0.09
    -angle
    0.09
     yakho
    0.09
     الرابعة
    0.09
     ukusuka
    0.09
     Angle
    0.09
     negatif
    0.09
     situe
    0.08
     angles
    0.08
    Activations Density 0.040%

    No Known Activations