© 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. 6266
    Prev
    Next
    INDEX
    Explanations

    audio file formats

    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
     photographic
    -0.10
    	screen
    -0.09
     eyesight
    -0.09
     vitrage
    -0.09
     skincare
    -0.09
     photograph
    -0.09
     photography
    -0.09
    Camera
    -0.09
    _SCREEN
    -0.09
     화면
    -0.09
    POSITIVE LOGITS
     WAV
    0.25
     wav
    0.21
     PCM
    0.21
    .wav
    0.20
    wav
    0.19
     pcm
    0.19
    PCM
    0.18
    _pcm
    0.18
    .wave
    0.17
     wave
    0.17
    Activations Density 0.024%

    No Known Activations