© 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. 19-RESID-POST-AA
    11. 18977
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -sign
    -0.09
    ity
    -0.09
    -0.07
    -total
    -0.07
    -known
    -0.07
     assin
    -0.07
     signs
    -0.07
    _SIGN
    -0.07
    ly
    -0.07
    geteilt
    -0.07
    POSITIVE LOGITS
     considérer
    0.16
     considering
    0.16
     considerar
    0.15
    考虑
    0.15
     considerando
    0.15
     Considering
    0.14
    Considering
    0.14
     considera
    0.14
     consid
    0.14
     consideran
    0.14
    Activations Density 0.001%
    No Known Activations