© 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. 49770
    Prev
    Next
    INDEX
    Explanations

    625

    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
     Features
    -0.09
     pegar
    -0.08
     muž
    -0.08
    .features
    -0.08
    .Features
    -0.08
     features
    -0.08
    Features
    -0.08
    -mail
    -0.07
    RAR
    -0.07
    .sky
    -0.07
    POSITIVE LOGITS
    625
    0.32
    624
    0.21
     processors
    0.20
    626
    0.19
    623
    0.17
    _processor
    0.16
    processors
    0.16
    627
    0.16
    Processors
    0.15
    _processors
    0.15
    Activations Density 0.020%

    No Known Activations