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. 78528
    Prev
    Next
    INDEX
    Explanations

    the

    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
     derechos
    -0.08
     matr
    -0.08
     stabbing
    -0.08
     vowel
    -0.08
     пур
    -0.07
     encant
    -0.07
     stripe
    -0.07
     coerc
    -0.07
     dunes
    -0.07
     captures
    -0.07
    POSITIVE LOGITS
     astronauts
    0.14
     spacecraft
    0.14
     astronaut
    0.14
     NASA
    0.13
     aboard
    0.13
    NASA
    0.12
     onboard
    0.11
     missions
    0.10
     missie
    0.10
     orbit
    0.10
    Activations Density 0.027%

    No Known Activations