© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 48745
    Prev
    Next
    INDEX
    Explanations

    L

    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
    ICLES
    -0.12
    JKLMNOP
    -0.11
    IZED
    -0.11
    OPLE
    -0.11
    IFICATIONS
    -0.11
    ORIES
    -0.11
    ARCHAR
    -0.11
    MENTS
    -0.11
    ONTAL
    -0.11
     LA
    -0.11
    POSITIVE LOGITS
    .h
    0.16
    hs
    0.15
    HS
    0.12
    sts
    0.12
    .H
    0.11
    side
    0.11
    .c
    0.11
    -value
    0.10
    cb
    0.10
    cm
    0.10
    Activations Density 0.005%

    No Known Activations