© 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. 5532
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    otherapist
    -0.09
     Tutor
    -0.08
    Tutor
    -0.08
    	Application
    -0.08
     profondeur
    -0.08
    .Objects
    -0.07
     Therapist
    -0.07
     Körper
    -0.07
    licate
    -0.07
     amala
    -0.07
    POSITIVE LOGITS
     oranges
    0.14
     citrus
    0.13
     stone
    0.11
     onions
    0.11
     berries
    0.11
     pine
    0.11
     mel
    0.11
     pears
    0.10
     grapes
    0.10
     Citrus
    0.10
    Activations Density 0.003%

    No Known Activations