© 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. 49125
    Prev
    Next
    INDEX
    Explanations

    cyrillic "А"

    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
    ന്റ
    -0.08
     učen
    -0.08
     Dolores
    -0.08
    ાત્મ
    -0.08
    ರ್ಪ
    -0.08
     voorbij
    -0.07
    নীত
    -0.07
     Dost
    -0.07
    ൂട്ട
    -0.07
     മരണ
    -0.07
    POSITIVE LOGITS
    cción
    0.09
    ria
    0.09
    жение
    0.08
    hanger
    0.08
    andeel
    0.08
    spa
    0.08
    spect
    0.08
     bringing
    0.08
    CIÓN
    0.08
    rea
    0.08
    Activations Density 0.003%

    No Known Activations