© 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. 103024
    Prev
    Next
    INDEX
    Explanations

    say "zeros"

    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
     ആദ്യ
    -0.08
    	initial
    -0.08
     First
    -0.07
     शुरुआत
    -0.07
     پہلی
    -0.07
     erste
    -0.07
    änge
    -0.07
    INGER
    -0.07
     మొద
    -0.07
    POSITIVE LOGITS
     deset
    0.10
     zeros
    0.10
     деся
    0.09
    -ten
    0.09
     newline
    0.09
     ten
    0.08
     blanks
    0.08
    Attach
    0.08
     দশ
    0.08
     commas
    0.08
    Activations Density 0.002%

    No Known Activations