© 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. 47801
    Prev
    Next
    INDEX
    Explanations

    say "the ending -ades or -ota"

    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
    оруж
    -0.09
     Mali
    -0.09
     Dominion
    -0.08
    Invocation
    -0.08
    odule
    -0.08
    оволь
    -0.08
     Dur
    -0.08
     tuple
    -0.08
    _Type
    -0.07
    Domin
    -0.07
    POSITIVE LOGITS
    ्यता
    0.09
     Hugo
    0.08
    keiten
    0.08
    anders
    0.08
    ा�
    0.07
    ایی
    0.07
    	Debug
    0.07
     �
    0.07
    ाऱ्या
    0.07
    허
    0.07
    Activations Density 0.000%

    No Known Activations