© 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. 5821
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    .sales
    -0.09
     ung
    -0.08
    NPC
    -0.08
     postgres
    -0.08
    owa
    -0.08
     Disneyland
    -0.08
     retro
    -0.08
    NASA
    -0.07
    postgres
    -0.07
    Arduino
    -0.07
    POSITIVE LOGITS
     Wave
    0.16
    Wave
    0.14
     wave
    0.12
    _wave
    0.12
    wave
    0.12
    .wave
    0.11
     X
    0.11
     Kash
    0.10
     Bench
    0.10
     waveform
    0.10
    Activations Density 0.002%

    No Known Activations