© 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. 19-RESID-POST-AA
    11. 103103
    Prev
    Next
    INDEX
    Explanations

    1

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '{
    -0.08
    ाथ
    -0.08
    ,a
    -0.08
    -Air
    -0.08
    issa
    -0.08
    azes
    -0.08
    ,N
    -0.08
    	strcat
    -0.08
    	as
    -0.08
     والأ
    -0.08
    POSITIVE LOGITS
    these
    0.09
     these
    0.09
    did
    0.08
    roscopic
    0.08
     tych
    0.08
    both
    0.08
     этих
    0.08
     жоқ
    0.08
     half
    0.08
    state
    0.08
    Activations Density 0.030%

    No Known Activations