© 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. 47542
    Prev
    Next
    INDEX
    Explanations

    linestyle

    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
    ต้องฝาก
    -0.08
     Titel
    -0.08
    _BO
    -0.08
     melden
    -0.08
    _Title
    -0.08
     meldt
    -0.08
    Titel
    -0.08
     BUSINESS
    -0.08
     પડશે
    -0.08
     heroin
    -0.08
    POSITIVE LOGITS
     linestyle
    0.20
    (alpha
    0.15
    .alpha
    0.15
     alpha
    0.14
    .grid
    0.14
    -alpha
    0.13
    Alpha
    0.13
    alpha
    0.13
    _alpha
    0.12
    <Grid
    0.12
    Activations Density 0.001%

    No Known Activations