© 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. 23-RESID-POST-AA
    11. 5788
    Prev
    Next
    INDEX
    Explanations

    pathlib

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Erick
    -0.09
     kwanza
    -0.08
     seizoen
    -0.08
    Hosted
    -0.08
    EDIT
    -0.08
     আন্দ
    -0.08
     exempel
    -0.08
     Staffel
    -0.08
     atun
    -0.08
     Donald
    -0.08
    POSITIVE LOGITS
     pathlib
    0.19
    .Path
    0.18
    (Path
    0.17
     Path
    0.16
    	Path
    0.15
     Pos
    0.14
    (path
    0.14
    (Pos
    0.13
    .cwd
    0.13
    (Paths
    0.13
    Activations Density 0.007%

    No Known Activations