© 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. 96654
    Prev
    Next
    INDEX
    Explanations

    cyrillic "о"

    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
     '/'
    -0.08
    Hallo
    -0.08
     "','
    -0.08
     يرت
    -0.07
    racht
    -0.07
     مرحلة
    -0.07
    Nor
    -0.07
    Introdu
    -0.07
     وعن
    -0.07
    Into
    -0.07
    POSITIVE LOGITS
    ки
    0.11
    וויס
    0.09
    ਕ
    0.09
    ਇ
    0.09
    laşdır
    0.08
    dev
    0.08
     tm
    0.08
    ਵੀ
    0.08
    ევ
    0.08
    િયો
    0.08
    Activations Density 0.000%

    No Known Activations