© 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. 23-RESID-POST-AA
    11. 5950
    Prev
    Next
    INDEX
    Explanations

    Univers

    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
    43
    -0.10
    rifice
    -0.09
    42
    -0.08
    Flip
    -0.08
    625
    -0.08
    (owner
    -0.08
    431
    -0.08
    127
    -0.08
    /card
    -0.08
    	with
    -0.08
    POSITIVE LOGITS
    itéit
    0.11
    ització
    0.11
    azzjoni
    0.11
    anhia
    0.11
    ució
    0.11
    amentul
    0.11
    éncia
    0.11
     Oy
    0.10
    edoria
    0.10
     Concello
    0.10
    Activations Density 0.006%

    No Known Activations