© 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. 110661
    Prev
    Next
    INDEX
    Explanations

    of

    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
    far
    -0.08
    Far
    -0.08
     flying
    -0.08
     compre
    -0.08
    leasing
    -0.08
     зат
    -0.07
     Mustang
    -0.07
     jaw
    -0.07
    track
    -0.07
     cresc
    -0.07
    POSITIVE LOGITS
    ಿಮ
    0.09
    0.09
    _PROPERTIES
    0.08
     ನಡೆಸ
    0.08
    ായ
    0.08
    neh
    0.08
    ಿಸಿದ
    0.08
     Abram
    0.08
    uga
    0.07
    _properties
    0.07
    Activations Density 0.016%
    No Known Activations