© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 51985
    Prev
    Next
    INDEX
    Explanations

    say "bles"

    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
    gna
    -0.09
    алог
    -0.09
     Geld
    -0.08
     Ausgang
    -0.08
     äh
    -0.08
     limp
    -0.08
     gert
    -0.08
    აპირ
    -0.08
     Sozial
    -0.07
    ponents
    -0.07
    POSITIVE LOGITS
    bles
    0.11
    osive
    0.09
    quoise
    0.09
    _Element
    0.08
    shaller
    0.08
    ibble
    0.08
     Vader
    0.08
    vival
    0.07
    vell
    0.07
    vem
    0.07
    Activations Density 0.001%

    No Known Activations