© 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. 63250
    Prev
    Next
    INDEX
    Explanations

    Auxiliary/common verbs

    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
    <Cell
    -0.08
     атмос
    -0.07
     turma
    -0.07
    atisfactory
    -0.07
     diter
    -0.07
     урок
    -0.07
    ాస్
    -0.07
    aug
    -0.07
    セル
    -0.07
     compile
    -0.07
    POSITIVE LOGITS
    Typically
    0.12
     ഇത്ത
    0.11
     typically
    0.11
     Typically
    0.10
     yleensä
    0.10
     ilyen
    0.10
     doorga
    0.10
     costuma
    0.10
     normalerweise
    0.10
    typically
    0.10
    Activations Density 0.324%

    No Known Activations