© 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. 48584
    Prev
    Next
    INDEX
    Explanations

    fuzzy membership

    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
     cookie
    -0.09
     checksum
    -0.08
     jackpot
    -0.08
    cookie
    -0.08
    .cookie
    -0.08
    HEADER
    -0.08
    Winvalid
    -0.08
     shotgun
    -0.08
     countdown
    -0.08
    Recycler
    -0.08
    POSITIVE LOGITS
     fuzzy
    0.28
     fuzz
    0.22
     membership
    0.22
     Membership
    0.21
    uzzy
    0.21
    Membership
    0.20
    membership
    0.20
     memberships
    0.19
     linguistic
    0.19
     crisp
    0.18
    Activations Density 0.008%

    No Known Activations