© 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. 11-RESID-POST-AA
    11. 71376
    Prev
    Next
    INDEX
    Explanations

    face

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hobby
    -0.07
    ARSE
    -0.07
     ere
    -0.07
     快
    -0.07
    intl
    -0.07
     glean
    -0.07
    erad
    -0.07
    amau
    -0.07
     बित
    -0.07
     coloring
    -0.07
    POSITIVE LOGITS
     payouts
    0.10
     payable
    0.09
    _future
    0.09
     потріб
    0.08
     Fabio
    0.08
     지급
    0.08
     lágrimas
    0.08
     payout
    0.08
     للبيع
    0.08
    об
    0.08
    Activations Density 0.005%

    No Known Activations