© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49594
    Prev
    Next
    INDEX
    Explanations

    IM

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    тичес
    -0.08
    orm
    -0.08
    ιστα
    -0.07
    itsin
    -0.07
    ίνη
    -0.07
    iorn
    -0.07
    ósitos
    -0.07
    אָר
    -0.07
     کس
    -0.07
    those
    -0.07
    POSITIVE LOGITS
    MEDIATE
    0.15
    PLICIT
    0.14
    AGES
    0.14
    PLICATION
    0.12
    PLIED
    0.12
    AGING
    0.12
    AGEN
    0.11
    AGEM
    0.11
    AGER
    0.10
    itating
    0.10
    Activations Density 0.008%

    No Known Activations