© 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. 19074
    Prev
    Next
    INDEX
    Explanations

    zoom

    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
     code
    -0.08
     manière
    -0.08
     solely
    -0.08
    コード
    -0.08
    沉
    -0.07
    ள
    -0.07
    โก
    -0.07
    _hex
    -0.07
    да
    -0.07
     Hex
    -0.07
    POSITIVE LOGITS
    orphic
    0.11
    Levels
    0.10
    obox
    0.10
    ookeeper
    0.10
     nkauj
    0.10
    ologically
    0.09
    orphism
    0.09
    obooks
    0.09
     levels
    0.09
    ocaust
    0.09
    Activations Density 0.007%

    No Known Activations