© 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. 18572
    Prev
    Next
    INDEX
    Explanations

    following instructions

    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
     (
    -0.13
    .↵↵
    -0.12
    ,
    -0.11
    ^
    -0.10
    )↵↵
    -0.10
    08
    -0.09
    /
    -0.09
    _{
    -0.09
    (
    -0.09
    ²
    -0.08
    POSITIVE LOGITS
     NEVER
    0.12
     uitsluitend
    0.12
    <|start|>
    0.12
    回复
    0.12
     বাংলা
    0.12
     everytime
    0.12
     മലയാള
    0.12
     nooit
    0.12
    ,you
    0.11
     ALWAYS
    0.11
    Activations Density 0.083%

    No Known Activations