© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47187
    Prev
    Next
    INDEX
    Explanations

    giving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _IND
    -0.08
    roe
    -0.08
    raine
    -0.08
    	Err
    -0.08
     Acute
    -0.08
    ZN
    -0.07
    .err
    -0.07
    Delimited
    -0.07
    soe
    -0.07
    -0.07
    POSITIVE LOGITS
     generously
    0.10
     wholeheartedly
    0.10
     generosity
    0.10
    -hearted
    0.10
     вещей
    0.09
     베
    0.09
     pengar
    0.08
     cảm
    0.08
    ค้น
    0.08
    तीय
    0.08
    Activations Density 0.026%
    No Known Activations