INDEX

Explanations

to

np_max-act · gemini-2.0-flash

Explanation could not be parsed.

eleuther_acts_top20 · gpt-5-mini Triggered by @tatsatx

phrases about the discovery and significance of a long-lost art masterpiece.

oai_token-act-pair · gpt-5-nano Triggered by @tatsatx

<|startoftext|>

np_max-act-logits · gpt-5-mini Triggered by @tatsatx

the start-of-text token (the very beginning of the document).

oai_token-act-pair · gpt-5-mini Triggered by @tatsatx

New Auto-Interp

Configuration

andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0

Dataset (Dashboard)

Various

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-around

-0.08

 मुझे

-0.08

 Injectable

-0.07

Stan

-0.07

verd

-0.07

'etiti

-0.07

 המא

-0.07

 incluso

-0.07

 fiquei

-0.07

िकेट

-0.07

POSITIVE LOGITS

Hen

0.08

 Kerala

0.08

 Madrid

0.08

0.07

 fiesta

0.07

ugh

0.07

 respectivas

0.07

Kü

0.07

sir

0.07

ur

0.07

Activations Density 0.031%

to

Explanation could not be parsed.

phrases about the discovery and significance of a long-lost art masterpiece.

<|startoftext|>

the start-of-text token (the very beginning of the document).

No Comments

No Known Activations