Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76416
    Prev
    Next
    INDEX
    Explanations

    Gnosticism and esoteric knowledge

    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
    સ્થ
    -0.08
     Stats
    -0.08
     turnout
    -0.08
     المش
    -0.08
     burger
    -0.08
    سل
    -0.08
     Constraints
    -0.08
     Deadline
    -0.07
     subsidy
    -0.07
     Guaranteed
    -0.07
    POSITIVE LOGITS
     mystical
    0.12
     эз
    0.11
     ecstatic
    0.10
     decipher
    0.10
     divine
    0.10
     алх
    0.10
     metaph
    0.10
     Tarot
    0.10
     persecut
    0.10
    Ether
    0.09
    Activations Density 0.031%

    No Known Activations