© 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. 11-RESID-POST-AA
    11. 47891
    Prev
    Next
    INDEX
    Explanations

    Ferries and vehicular transport

    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
    eteilig
    -0.08
    IZZ
    -0.08
    ønd
    -0.08
     handset
    -0.08
    izzle
    -0.08
    IPS
    -0.08
    _PATTERN
    -0.08
     Abuja
    -0.08
    öld
    -0.07
    テレビ
    -0.07
    POSITIVE LOGITS
     payload
    0.15
    _payload
    0.13
    payload
    0.13
    Payload
    0.12
     Payload
    0.12
     passenger
    0.11
    .payload
    0.11
    	payload
    0.11
     cargo
    0.11
     passengers
    0.11
    Activations Density 0.069%

    No Known Activations