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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12260
    Prev
    Next
    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cycl
    -0.07
    ammik
    -0.07
    kins
    -0.07
    DEM
    -0.07
    itz
    -0.07
    Sac
    -0.07
    St
    -0.07
    HV
    -0.07
     మె
    -0.07
     has
    -0.06
    POSITIVE LOGITS
     mesma
    0.09
    439
    0.09
     indústria
    0.08
     Rifle
    0.08
     esquerda
    0.08
     droite
    0.08
    иваются
    0.08
     installers
    0.08
    pluck
    0.07
     Plasma
    0.07
    Activations Density 0.000%

    No Known Activations