© 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. 3-RESID-POST-AA
    11. 1409
    Prev
    Next
    INDEX
    Explanations

    König

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anto
    -0.08
    .rm
    -0.07
     detaine
    -0.07
     rms
    -0.07
    arer
    -0.07
     volumes
    -0.07
    683
    -0.07
     mv
    -0.07
    lage
    -0.07
    র্ড
    -0.07
    POSITIVE LOGITS
    Applied
    0.08
     entidade
    0.08
    Mechanical
    0.08
    Etat
    0.08
     مص
    0.08
    Computed
    0.07
    Tin
    0.07
     economies
    0.07
    ENGINE
    0.07
    Faire
    0.07
    Activations Density 0.014%

    No Known Activations