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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 102507
    Prev
    Next
    INDEX
    Explanations

    !=

    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
    ia
    -0.09
     and
    -0.08
     এবং
    -0.08
    gzip
    -0.08
    jali
    -0.08
     اور
    -0.08
     تأس
    -0.07
    c
    -0.07
    ('
    -0.07
    apo
    -0.07
    POSITIVE LOGITS
     SUCCESS
    0.13
    成功
    0.11
     successful
    0.11
     Successful
    0.11
    _SUCCESS
    0.11
     સફળ
    0.11
    _success
    0.11
     ಯಶ
    0.10
    SUCCESS
    0.10
     réussite
    0.10
    Activations Density 0.000%

    No Known Activations