© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47469
    Prev
    Next
    INDEX
    Explanations

    overd

    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
     турында
    -0.09
    aycast
    -0.08
    Tile
    -0.08
     жөнүндө
    -0.08
    Tiger
    -0.08
    adomo
    -0.08
    -0.08
     тухай
    -0.08
    acency
    -0.08
     талаар
    -0.08
    POSITIVE LOGITS
    ubs
    0.09
    rafts
    0.09
    rafted
    0.09
    raft
    0.08
    687
    0.08
    RAFT
    0.08
    amped
    0.08
    oses
    0.08
    rafting
    0.08
    enture
    0.08
    Activations Density 0.001%

    No Known Activations