© 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. 11-RESID-POST-AA
    11. 31123
    Prev
    Next
    INDEX
    Explanations

    artifactory elasticsearch

    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
    NN
    -0.08
     spars
    -0.08
    VID
    -0.07
     constellation
    -0.07
     Casual
    -0.07
     Lives
    -0.07
    FL
    -0.07
     CF
    -0.07
     Entscheidungen
    -0.07
     lives
    -0.07
    POSITIVE LOGITS
     kayak
    0.09
     Pale
    0.08
     additives
    0.08
    klju
    0.08
     yug
    0.08
     gost
    0.08
     botan
    0.08
     startup
    0.08
     overgang
    0.08
     recibe
    0.08
    Activations Density 0.002%

    No Known Activations