© 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. 50899
    Prev
    Next
    INDEX
    Explanations

    say reverse

    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
     essayé
    -0.09
    ữu
    -0.09
    ajada
    -0.08
     reduced
    -0.08
    aliselt
    -0.08
     cấu
    -0.08
     Vorm
    -0.08
     nooit
    -0.07
    vorm
    -0.07
     Уже
    -0.07
    POSITIVE LOGITS
     flips
    0.39
     flipping
    0.37
     flip
    0.37
     Flip
    0.33
    flip
    0.33
    Flip
    0.32
    _flip
    0.31
     flipped
    0.31
     reversing
    0.30
    .flip
    0.29
    Activations Density 0.099%

    No Known Activations