© 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. 12739
    Prev
    Next
    INDEX
    Explanations

    colon

    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
     rains
    -0.07
     вой
    -0.07
     appliance
    -0.07
     identity
    -0.07
     rhythm
    -0.07
    研
    -0.07
     contrast
    -0.07
     kontroll
    -0.07
     weak
    -0.07
     tokom
    -0.07
    POSITIVE LOGITS
     Scenes
    0.09
     scènes
    0.08
    Scenes
    0.08
    *******/↵
    0.08
    LOCATION
    0.08
     grootste
    0.07
    	Scene
    0.07
    评
    0.07
    	scene
    0.07
    	point
    0.07
    Activations Density 0.000%

    No Known Activations