© 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. 23-RESID-POST-AA
    11. 51079
    Prev
    Next
    INDEX
    Explanations

    It

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    даются
    -0.09
    даем
    -0.08
    ಿದ್ದಾರೆ
    -0.08
     example
    -0.08
    ರಾಗ
    -0.08
     הם
    -0.08
    даи
    -0.08
    മുള്ള
    -0.08
     olaraq
    -0.08
    دڙ
    -0.08
    POSITIVE LOGITS
    inerary
    0.21
    ’s
    0.17
    anium
    0.15
    ´s
    0.15
     rains
    0.15
    iner
    0.14
    érations
    0.14
    self
    0.14
    ération
    0.13
    érer
    0.13
    Activations Density 0.067%

    No Known Activations