© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12780
    Prev
    Next
    INDEX
    Explanations

    undefined

    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
     Ml
    -0.08
     Fro
    -0.08
     أر
    -0.07
     Cred
    -0.07
     beliebtesten
    -0.07
     credibility
    -0.07
     Advantages
    -0.07
     evacuated
    -0.07
    ónicos
    -0.07
    enga
    -0.07
    POSITIVE LOGITS
    VISIBLE
    0.08
    akw
    0.08
    >>>>>>>>
    0.07
     meen
    0.07
    KW
    0.07
    Sed
    0.07
    HAL
    0.07
    努
    0.07
    employment
    0.07
     communes
    0.07
    Activations Density 0.001%

    No Known Activations