© 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. 94855
    Prev
    Next
    INDEX
    Explanations

    Photography

    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
    Generation
    -0.08
     Generation
    -0.08
     generation
    -0.08
     undis
    -0.07
     Phase
    -0.07
     Font
    -0.07
    loa
    -0.07
     arr
    -0.07
     recycler
    -0.07
     cycle
    -0.07
    POSITIVE LOGITS
     scenery
    0.12
     filmed
    0.12
     scen
    0.10
     fotograf
    0.10
     tim
    0.09
     panor
    0.09
     scenes
    0.09
     입력
    0.09
     scènes
    0.09
     sujetos
    0.09
    Activations Density 0.032%

    No Known Activations