© 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. 47500
    Prev
    Next
    INDEX
    Explanations

    CHE

    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
    -bound
    -0.08
     handle
    -0.08
    	handle
    -0.08
    _BOUND
    -0.08
    ائرات
    -0.07
    .Concat
    -0.07
    -band
    -0.07
    興
    -0.07
    েল
    -0.07
    ahlobo
    -0.07
    POSITIVE LOGITS
     dicen
    0.09
    ungu
    0.09
     Freeze
    0.08
    MY
    0.08
    freeze
    0.08
    _fin
    0.08
     financieros
    0.08
     messing
    0.08
     Om
    0.08
     freeze
    0.08
    Activations Density 0.000%

    No Known Activations