© 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. 6502
    Prev
    Next
    INDEX
    Explanations

    -par

    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
    syon
    -0.09
     Rö
    -0.09
    ohi
    -0.09
    otiques
    -0.09
    ichier
    -0.09
    OME
    -0.08
    LOUD
    -0.08
    otics
    -0.08
    reiche
    -0.08
    wuka
    -0.08
    POSITIVE LOGITS
    allel
    0.18
    alleled
    0.16
    alle
    0.14
    ALLE
    0.12
     parallel
    0.10
    pendicular
    0.09
     parallèle
    0.09
    alles
    0.08
    Parallel
    0.08
    alled
    0.08
    Activations Density 0.001%

    No Known Activations