© 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. 19-RESID-POST-AA
    11. 18837
    Prev
    Next
    INDEX
    Explanations

    versions of "most"

    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
    $b
    -0.10
     ('$
    -0.09
    $x
    -0.09
    $j
    -0.09
    $t
    -0.09
     ("\
    -0.09
    $v
    -0.09
     cheesy
    -0.08
    $m
    -0.08
    $r
    -0.08
    POSITIVE LOGITS
     most
    0.12
     maioria
    0.11
     अधिकांश
    0.11
    :↵↵
    0.11
     наиболее
    0.11
     सबसे
    0.11
     plupart
    0.11
    most
    0.11
     these
    0.10
     Parmi
    0.10
    Activations Density 0.081%

    No Known Activations