© 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. 3-RESID-POST-AA
    11. 2642
    Prev
    Next
    INDEX
    Explanations

    list

    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
    imu
    -0.08
    MES
    -0.08
     cabbage
    -0.07
    cond
    -0.07
     Perm
    -0.07
    올
    -0.07
    rain
    -0.07
     conditioned
    -0.07
    BMW
    -0.07
     bells
    -0.07
    POSITIVE LOGITS
    🏻
    0.10
    🏼
    0.10
    اً
    0.09
    živ
    0.08
     говоря
    0.08
    -solving
    0.08
     paced
    0.08
     цел
    0.08
    任
    0.07
    usy
    0.07
    Activations Density 0.004%

    No Known Activations