Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2394
    Prev
    Next
    INDEX
    Explanations

    single

    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
     antibiotics
    -0.07
     tunne
    -0.07
     coul
    -0.07
     Qui
    -0.07
    SG
    -0.07
    Nev
    -0.07
    -ended
    -0.07
    (term
    -0.07
    ព
    -0.07
     Bd
    -0.07
    POSITIVE LOGITS
     Finds
    0.08
     Jade
    0.08
    imam
    0.07
     imposs
    0.07
    Trending
    0.07
     ואת
    0.07
     FMC
    0.07
    ULATION
    0.07
     Fib
    0.07
     Mixer
    0.07
    Activations Density 0.010%

    No Known Activations