© 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. 205
    Prev
    Next
    INDEX
    Explanations

    landscape

    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
     sedent
    -0.08
     Dishwasher
    -0.08
     Forms
    -0.07
     sinc
    -0.07
     domicili
    -0.07
    dés
    -0.07
    cket
    -0.07
     confe
    -0.07
     комплект
    -0.07
     '".
    -0.07
    POSITIVE LOGITS
     terrains
    0.09
     breathtaking
    0.08
     paysages
    0.08
     hend
    0.08
     landscapes
    0.08
     સુંદર
    0.08
     समुद
    0.08
     scenery
    0.08
     vistas
    0.08
     aband
    0.07
    Activations Density 0.006%

    No Known Activations