© 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. 6497
    Prev
    Next
    INDEX
    Explanations

    forum

    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
     ochron
    -0.09
     calm
    -0.08
    .erp
    -0.08
     confiance
    -0.08
     مرتب
    -0.07
    Irish
    -0.07
     princes
    -0.07
     σο
    -0.07
    _attachment
    -0.07
    Independent
    -0.07
    POSITIVE LOGITS
     Forum
    0.14
     Forums
    0.13
     forum
    0.12
     forums
    0.12
     форум
    0.11
     Fórum
    0.11
     المنتدى
    0.11
     Circus
    0.11
    论坛
    0.11
    Forum
    0.10
    Activations Density 0.008%

    No Known Activations