© 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. 5572
    Prev
    Next
    INDEX
    Explanations

    Machine learning models

    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
     الجما
    -0.09
    117
    -0.08
    ︎
    -0.08
    ٰ
    -0.08
    ?...
    -0.08
    
    -0.08
    posedge
    -0.08
    Resolvable
    -0.08
    ...»
    -0.08
    Been
    -0.08
    POSITIVE LOGITS
    _df
    0.09
    _feats
    0.09
    _kwargs
    0.09
    _processor
    0.09
    नेट
    0.08
    _handler
    0.08
    _probs
    0.08
    ाईं
    0.08
    _fn
    0.08
    _sizes
    0.08
    Activations Density 0.007%

    No Known Activations