© 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. 50877
    Prev
    Next
    INDEX
    Explanations

    say "the ending a or o"

    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
    ó
    -0.22
    ou
    -0.22
    ió
    -0.15
    ouple
    -0.13
    OU
    -0.12
    ले
    -0.11
    -ou
    -0.11
    ल्या
    -0.10
    ouer
    -0.10
    ली
    -0.10
    POSITIVE LOGITS
    Countdown
    0.09
    Checking
    0.08
    CHK
    0.08
     Countdown
    0.08
    Downloading
    0.07
    Checkout
    0.07
    _CHECK
    0.07
    Chunk
    0.07
    Checks
    0.07
     vowed
    0.07
    Activations Density 0.010%

    No Known Activations